Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.37 as permitted sender) client-ip=23.128.96.37;
From:   Srikar Dronamraju <srikar@linux.vnet.ibm.com>
To:     Ingo Molnar <mingo@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Valentin Schneider <vschneid@redhat.com>
Cc:     LKML <linux-kernel@vger.kernel.org>,
        Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Subject: [PATCH] sched/fair: Enable group_asym_packing in find_idlest_group
Date:   Wed, 18 Oct 2023 21:20:35 +0530
Message-ID: <20231018155036.2314342-1-srikar@linux.vnet.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Current scheduler code doesn't handle SD_ASYM_PACKING in the
find_idlest_cpu path. On few architectures, like Powerpc, cache is at a
core. Moving threads across cores may end up in cache misses.

While asym_packing can be enabled above SMT level, enabling Asym packing
across cores could result in poorer performance due to cache misses.
However if the initial task placement via find_idlest_cpu does take
Asym_packing into consideration, then scheduler can avoid asym_packing
migrations. This will result in lesser migrations and better packing and
better overall performance.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
 kernel/sched/fair.c | 33 ++++++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cb225921bbca..7164f79a3d13 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9931,11 +9931,13 @@ static int idle_cpu_without(int cpu, struct task_struct *p)
  * @group: sched_group whose statistics are to be updated.
  * @sgs: variable to hold the statistics for this group.
  * @p: The task for which we look for the idlest group/CPU.
+ * @this_cpu: current cpu
  */
 static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 					  struct sched_group *group,
 					  struct sg_lb_stats *sgs,
-					  struct task_struct *p)
+					  struct task_struct *p,
+					  int this_cpu)
 {
 	int i, nr_running;
 
@@ -9972,6 +9974,11 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
 
 	}
 
+	if (sd->flags & SD_ASYM_PACKING && sgs->sum_h_nr_running &&
+			sched_asym_prefer(group->asym_prefer_cpu, this_cpu)) {
+		sgs->group_asym_packing = 1;
+	}
+
 	sgs->group_capacity = group->sgc->capacity;
 
 	sgs->group_weight = group->group_weight;
@@ -10012,8 +10019,17 @@ static bool update_pick_idlest(struct sched_group *idlest,
 			return false;
 		break;
 
-	case group_imbalanced:
 	case group_asym_packing:
+		if (sched_asym_prefer(group->asym_prefer_cpu, idlest->asym_prefer_cpu)) {
+			int busy_cpus = idlest_sgs->group_weight - idlest_sgs->idle_cpus;
+
+			busy_cpus -= (sgs->group_weight - sgs->idle_cpus);
+			if (busy_cpus >= 0)
+				return true;
+		}
+		return false;
+
+	case group_imbalanced:
 	case group_smt_balance:
 		/* Those types are not used in the slow wakeup path */
 		return false;
@@ -10080,7 +10096,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 			sgs = &tmp_sgs;
 		}
 
-		update_sg_wakeup_stats(sd, group, sgs, p);
+		update_sg_wakeup_stats(sd, group, sgs, p, this_cpu);
 
 		if (!local_group && update_pick_idlest(idlest, &idlest_sgs, group, sgs)) {
 			idlest = group;
@@ -10112,6 +10128,17 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 	if (local_sgs.group_type > idlest_sgs.group_type)
 		return idlest;
 
+	if (idlest_sgs.group_type == group_asym_packing) {
+		if (sched_asym_prefer(idlest->asym_prefer_cpu, local->asym_prefer_cpu)) {
+			int busy_cpus = local_sgs.group_weight - local_sgs.idle_cpus;
+
+			busy_cpus -= (idlest_sgs.group_weight - idlest_sgs.idle_cpus);
+			if (busy_cpus >= 0)
+				return idlest;
+		}
+		return NULL;
+	}
+
 	switch (local_sgs.group_type) {
 	case group_overloaded:
 	case group_fully_busy:
-- 
2.31.1